Specimen data information processing method, system, device and storage medium

Abstract

The present invention relates to a specimen data information processing method, system, device and storage medium, the method comprising: performing multi-stage separation processing on the acquired original specimen data to obtain specimen image data and specimen type data; performing node analysis processing on the specimen image data and specimen type data in sequence to obtain image node data and feature node data; performing image cutting processing on the specimen image data according to the image node data to obtain a specimen region image, performing image analysis on the specimen region image to obtain specimen image information, performing feature extraction on the specimen type data according to the feature node data to obtain feature type data, and performing structural analysis on the feature type data to obtain specimen type information; performing association analysis and node extraction on the specimen region image and the feature type data to obtain specimen association data and pathology association nodes. The present invention can comprehensively, quickly and accurately parse multi-dimensional data.

Description

Technical Field

[0001] The present invention relates to the technical field of specimen data, and in particular to a specimen data information processing method, system, device and storage medium. Background Art

[0002] In the field of contemporary biomedical research and clinical diagnosis, with the rapid development of high-throughput imaging technology and biological tissue sample libraries, the scale and complexity of specimen data have increased dramatically. However, traditional specimen analysis methods often focus on single-dimensional data analysis of ward specimens, ignoring the inherent connections between data and deep information mining, resulting in one-sidedness and incompleteness in the pathological analysis results of specimens. At the same time, specimen data usually contains complex image information and fine pathological features, but traditional specimen analysis methods are inefficient in data separation and preliminary processing, making it difficult to quickly and accurately separate useful information, affecting the timeliness and accuracy of subsequent analysis. Summary of the invention

[0003] The main purpose of the present invention is to provide a specimen data information processing method, system, device and storage medium, which can comprehensively, quickly and accurately analyze multi-dimensional data.

[0004] To achieve the above object, the present invention provides a method for processing specimen data information, comprising:

[0005] Perform multi-level separation processing on the acquired original specimen data to obtain specimen image data and specimen type data;

[0006] Performing node analysis processing on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data;

[0007] Performing image segmentation processing on the specimen image data according to the image node data to obtain a specimen region image, performing image analysis on the specimen region image to obtain specimen image information,

[0008] Extracting features of the specimen type data according to the characteristic node data to obtain characteristic type data, and performing structural analysis on the characteristic type data to obtain specimen type information;

[0009] Performing association analysis and node extraction on the specimen region image and the characteristic type data to obtain specimen-related data and pathology-related nodes;

[0010] A comprehensive analysis is performed based on the specimen association data in combination with the specimen image information and the specimen type information to obtain a specimen pathology report, and the specimen pathology report is encrypted according to the pathology association node to obtain an encrypted report.

[0011] Furthermore, the obtained original specimen data is subjected to multi-level processing to obtain specimen image data and specimen type data, including:

[0012] Extracting the original specimen data from the specimen tube, filtering the original specimen data according to a preset filtering rule to obtain initial cleansed data, and performing type separation on the initial cleansed data according to a preset type rule to obtain initial image data and initial structure data;

[0013] Determining whether the initial image data meets the preset pixel requirement, and when the initial image data does not meet the preset pixel requirement, reacquiring second initial image data, and fusing the second initial image data with the initial image data to obtain the specimen image data;

[0014] The initial structure data is segmented into corresponding type data blocks according to a preset multi-scale segmentation strategy, and the type data blocks are combed according to preset combing rules to obtain the specimen type data.

[0015] Furthermore, the step of sequentially performing node analysis on the specimen image data and the specimen type data to obtain image node data and feature node data includes:

[0016] Extracting image pixel blocks of the specimen image data, obtaining an image feature node candidate set by calculating a similarity matrix of the image pixel blocks and performing feature point recognition, and performing key node screening on the image feature node candidate set at different scales based on a preset multi-scale space rule to obtain the image node data;

[0017] Node analysis is performed on the specimen type data to obtain connection nodes and node types, key nodes are extracted from the connection nodes according to the node types to obtain a candidate set of characteristic nodes, node analysis is performed on the candidate set of characteristic nodes based on preset structural connection rules and non-key nodes are eliminated to obtain the characteristic node data.

[0018] Further, the image segmentation processing is performed on the specimen image data according to the image node data to obtain a specimen region image, and the image analysis is performed on the specimen region image to obtain specimen image information, including:

[0019] Mapping the image node data to the specimen image data to form a seed node, and locating the key feature area of ​​the specimen image data, calculating the regional similarity of the key feature area based on the seed node, and judging whether the regional similarity meets a preset similarity threshold, and when the regional similarity does not meet the similarity threshold, remapping the corresponding seed node and relocating the corresponding key feature area;

[0020] When the region similarity meets the similarity threshold, the specimen image data is subjected to multi-level region segmentation and optimization processing based on the key feature region to obtain the specimen region image;

[0021] Texture analysis, shape analysis and color analysis are performed on the specimen region image in sequence to obtain the specimen image information reflecting the specimen state information.

[0022] Further, the feature extraction of the specimen type data according to the characteristic node data to obtain the characteristic type data, and the structural analysis of the characteristic type data to obtain the specimen type information includes:

[0023] Performing node pathological feature analysis on the characteristic node data to obtain node characteristic data including node status, number of pathological nodes and node attributes, mapping the node characteristic data to the specimen type data, performing type feature analysis and extraction on the mapped specimen type data to obtain the characteristic type data;

[0024] Perform cluster analysis on the feature type data to obtain feature cluster data, perform grid analysis on the feature type data to obtain structural connection relationships, perform state analysis on the feature type data and the structural connection relationships to obtain specimen state information, and combine the feature type data, the structural connection relationships and the specimen state information to obtain the specimen type information.

[0025] Furthermore, the performing of association analysis and node extraction on the specimen region image and the feature type data to obtain specimen-related data and pathology-related nodes includes:

[0026] Mapping the characteristic type data onto the specimen region image to obtain a corresponding specimen mapping image, performing mapping analysis on the specimen mapping image to obtain a mapping relationship between the characteristic type data and the specimen region image, extracting overlapping nodes of the characteristic type data and the specimen region image from the specimen mapping image based on the mapping relationship, and performing pathological correlation analysis on the overlapping nodes to obtain the pathological correlation nodes;

[0027] The mapping image is subjected to association connection analysis according to the mapping relationship and the pathology-related nodes to obtain the specimen-related data.

[0028] Furthermore, the specimen pathology report is obtained by performing a comprehensive analysis based on the specimen association data in combination with the specimen image information and the specimen type information, and the specimen pathology report is encrypted according to the pathology association node to obtain an encrypted report, including:

[0029] Extracting corresponding connection points of the specimen image information and the specimen type information respectively according to the specimen association data to obtain image association points and structure association points, performing correlation analysis on the image association points and the structure association points to obtain corresponding connection information, correlating and connecting the specimen image information and the specimen type information according to the connection information and mapping them to a preset blank three-dimensional model to obtain a specimen three-dimensional model, performing state analysis on the specimen three-dimensional model according to the pathology association node to obtain state information, comprehensively correcting the state information according to the specimen image information and the specimen type information to obtain specimen comprehensive information, and generating the corresponding specimen pathology report based on the specimen comprehensive information;

[0030] According to a preset encryption rule, corresponding specific node data is randomly extracted from the pathology-related nodes, the specific node data is converted into encrypted node data for encryption, specimen node data about the node is extracted from the specimen pathology report, all specimen node data in the specimen pathology report are replaced with the encrypted node data, and replacement position data of the specimen node data is recorded to obtain a replacement report;

[0031] The extracted specimen node data is encrypted according to preset encryption rules to obtain corresponding encrypted data, the replacement position data is converted into a corresponding decryption password, and the encrypted data, decryption password and replacement report are integrated to obtain the encrypted report.

[0032] The present invention also provides a specimen data information processing system, which is applied to any one of the specimen data information processing methods described above, comprising:

[0033] An acquisition module, the acquisition module is used to perform multi-stage separation processing on the acquired original specimen data to obtain specimen image data and specimen type data;

[0034] A separation module, the separation module is used to perform node analysis processing on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data;

[0035] A cutting module, wherein the cutting module is used to perform image cutting processing on the specimen image data according to the image node data to obtain a specimen area image, and perform image analysis on the specimen area image to obtain specimen image information.

[0036] An analysis module, the analysis module is used to extract features of the specimen type data according to the characteristic node data to obtain characteristic type data, and perform structural analysis on the characteristic type data to obtain specimen type information;

[0037] A processing module, the processing module is used to perform association analysis and node extraction on the specimen area image and the feature type data to obtain specimen-related data and pathology-related nodes;

[0038] A control module is used to perform a comprehensive analysis based on the specimen association data in combination with the specimen image information and the specimen type information to obtain a specimen pathology report, and to encrypt the specimen pathology report according to the pathology association node to obtain an encrypted report.

[0039] The present invention also provides a specimen data information processing method and device, comprising:

[0040] Memory, used to store programs;

[0041] The processor is used to execute the program to implement each step of any one of the above-mentioned methods for processing sample data information.

[0042] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0043] The present invention provides the following beneficial effects:

[0044] Through multi-level separation processing, the original specimen data is effectively divided into image data and structural data. This process not only optimizes data management, but also lays the foundation for subsequent refined analysis. The node analysis technology is used to process image and structural data separately, which improves the pertinence and accuracy of data processing and makes the extraction of key information more efficient. Image cutting processing is based on image node data, which can accurately segment specimen areas with specific significance, and then obtain richer image information through image analysis. At the same time, the extraction and analysis of feature type data reveals the microscopic structural characteristics inside the specimen. The combination of the two greatly enhances the understanding and mining of deep-level information of biological specimens. Based on the comprehensive analysis of specimen-related data, image information and structural information, the generated specimen pathology report is more comprehensive and in-depth, providing more reliable and valuable reference for researchers and clinicians. The use of pathology-related nodes to encrypt the report innovatively combines bioinformatics and information security technology, which not only ensures the confidentiality of the report content, but also ensures the security of the data exchange process, which meets the current strict requirements for the protection of personal health information. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a specimen data information processing method provided by the present invention;

[0046] Figure 2 It is a structural diagram of a specimen data information processing system provided by the present invention;

[0047] Figure 3 It is a structural diagram of a specimen data information processing device provided by the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0051] Reference Figure 1 To achieve the above purpose, the present invention provides a method for processing sample data information, comprising:

[0052] Step S1: performing multi-level separation processing on the acquired original specimen data to obtain specimen image data and specimen type data;

[0053] Step S2: performing node analysis on the specimen image data and the specimen type data in turn to obtain image node data and feature node data;

[0054] Step S3: performing image segmentation processing on the specimen image data according to the image node data to obtain a specimen region image, and performing image analysis on the specimen region image to obtain specimen image information;

[0055] Step S4: extracting features from the specimen type data according to the feature node data to obtain feature type data, and performing structural analysis on the feature type data to obtain specimen type information;

[0056] Step S5: performing association analysis and node extraction on the specimen region image and feature type data to obtain specimen association data and pathology association nodes;

[0057] Step S6: Perform comprehensive analysis based on the specimen association data combined with the specimen image information and the specimen type information to obtain a specimen pathology report, and encrypt the specimen pathology report according to the pathology association node to obtain an encrypted report.

[0058] Based on the above steps, the detailed steps are as follows:

[0059] Step S1: Preprocess the acquired original specimen data, including denoising, image enhancement, color correction and other operations. Process the preprocessed data through a multi-level separation method, including segmentation, edge detection and threshold segmentation based on image processing technology, and morphological operations and connected region analysis based on structural analysis. The original specimen data is separated into specimen image data and specimen type data through the processing method based on image processing technology and the method based on structural analysis.

[0060] Specimen image data refers to image information extracted from the original specimen data, including the specimen's visual appearance, texture, shape and other features. In the multi-stage separation process, feature information related to the specimen image is extracted through image processing algorithms and feature extraction methods, and saved as specimen image data.

[0061] Specimen type data refers to the structural information extracted from the original specimen data, including the cell structure, tissue structure, etc. of the specimen. Through multi-level separation processing, structural analysis algorithms and feature extraction methods, the key features of the specimen structure are extracted and saved as specimen type data.

[0062] Step S2: Perform node analysis on the specimen image data, detect and extract key nodes in the image through computer vision and image processing technology, including edge detection, corner detection, contour extraction and other methods, obtain important structural feature points or key positions in the specimen image, and save them as image node data.

[0063] Perform node analysis on specimen type data, detect and extract key nodes in the structure through structural analysis and image processing methods, including morphological operations, connected region analysis, shape matching and other methods, obtain important nodes or important structural features in the specimen structure, and save them as feature node data.

[0064] Image node data is the key node information extracted from the specimen image data. These key nodes represent important structures, key features or areas of interest in the specimen. Through node analysis and processing, the position, shape, size and other information of these nodes are obtained and saved as image node data.

[0065] Feature node data is key node information extracted from specimen type data. These key nodes represent important tissue structures, organ structures, or cell structures of the specimen. Through node analysis and processing, the location, morphology, hierarchical relationship and other information of these nodes are obtained and saved as feature node data.

[0066] Step S3: According to the key node information extracted from the image node data, the region of interest in the specimen image is determined, and the target region in the specimen image is separated from the background by using image processing techniques such as threshold segmentation and edge detection, thereby obtaining a specimen region image.

[0067] The obtained specimen area images are further analyzed, including morphological operations, texture analysis, color feature extraction and other methods, to extract the characteristic information of the specimen image, such as shape, texture characteristics, color distribution, etc., to obtain more detailed specimen image information.

[0068] Based on the analysis results of the specimen area image, the key information of the specimen image is extracted, including the location, size, shape, and other disease-related features of the lesion area. By analyzing the feature data of the specimen image, the specimen image information is obtained.

[0069] Step S4: Using the key node information extracted from the feature node data, determine the part of interest in the specimen structure, and extract the key features of the specimen structure by applying structural analysis and feature extraction methods, such as morphological operations, connected region analysis, shape matching, etc. The features include the shape, size, arrangement, etc. of the cells.

[0070] The extracted feature type data is further analyzed, including statistical analysis, pattern recognition, classification algorithms and other methods, to extract the feature type data. Based on the analysis results of the feature type data, the structural information of the specimen is extracted. The structural information includes the morphology, structural hierarchy, and abnormalities of the tissue structure of cells, tissues or organs. By analyzing the structural information of the specimen, the specimen type information is obtained.

[0071] Step S5: Perform feature matching and alignment on the specimen image information and structural information by using methods such as image registration, feature matching, and morphological alignment, so as to spatially correspond the image and structural information.

[0072] Based on the image and structural information after feature matching and alignment, association analysis is performed, including cell segmentation in image segmentation and cell type matching in structural analysis, association analysis between image features and structural features, etc., to obtain the results of the association analysis. Based on the results of the association analysis, a comprehensive analysis is performed to obtain specimen-associated data and pathology-associated nodes. The specimen-associated data includes the evaluation of pathological features, the location of abnormal areas, the identification of lesion types, etc.

[0073] Step S6: Perform a comprehensive analysis based on the specimen-associated data combined with the specimen image information and the specimen type information to form the results of the specimen analysis. The results include descriptions of pathological features, location and descriptions of abnormal areas, diagnosis of lesion types, etc. Based on the specimen analysis results, generate a specimen analysis report. The report is in a structured form and includes pathological descriptions, quantitative and qualitative analysis results and suggestions of images and structures, etc.

[0074] The specimen pathology report is encrypted according to the pathology association node to obtain an encrypted report.

[0075] The present invention provides a method for processing specimen data information. The original specimen data is effectively divided into image data and structural data through multi-level separation processing. This process not only optimizes data management, but also lays the foundation for subsequent refined analysis. The node analysis technology is used to process image and structural data respectively, which improves the pertinence and accuracy of data processing and makes the extraction of key information more efficient. Image cutting processing is based on image node data, which can accurately segment specimen areas with specific significance, and then obtain richer image information through image analysis. At the same time, the extraction and analysis of feature type data reveals the microscopic structural characteristics inside the specimen. The combination of the two greatly enhances the understanding and mining of deep-level information of biological specimens. Based on the comprehensive analysis of specimen-related data, image information and structural information, the generated specimen pathology report content is more comprehensive and in-depth, providing more reliable and valuable reference for scientific researchers and clinicians. The use of pathology-related nodes to encrypt the report innovatively combines bioinformatics and information security technology, which not only ensures the confidentiality of the report content, but also ensures the security in the data exchange process, which meets the current strict requirements for the protection of personal health information.

[0076] In one embodiment, the acquired raw specimen data is subjected to multi-level processing to obtain specimen image data and specimen type data, including:

[0077] The original specimen data is extracted from the specimen tube, wherein the specimen tube is stored in a pathological specimen collection platform and is used to store pathological specimens.

[0078] The original specimen data is filtered according to the preset filtering rules to remove possible noise and invalid data and obtain initial purified data. The filtering rules are defined based on standards such as color, brightness, and contrast to ensure that only data that meets the preset rules is retained.

[0079] Next, the initial cleansed data is separated into types according to preset type rules. The type rules are defined based on the characteristics, morphology or other attributes of the specimen. Through type separation, the initial cleansed data is divided into two parts: initial image data and initial structural data.

[0080] First, it is determined whether the initial image data meets the preset pixel requirements, including image resolution, pixel density, color mode, etc. If the initial image data does not meet the requirements, it is necessary to reacquire the second initial image data, and fuse the second initial image data with the initial image data, for example, using an image fusion algorithm, to obtain the final specimen image data.

[0081] For the initial structural data, a preset multi-scale segmentation strategy is used for segmentation processing, and it is segmented into corresponding type data blocks. The multi-scale segmentation strategy is defined based on the hierarchical structure, gradient information or other features of the image. The segmented type data blocks represent different structural elements or regions in the specimen. Subsequently, the type data blocks are combed according to the preset combing rules to obtain the specimen type data. The combing rules include morphological operations, edge detection and texture analysis on the type data blocks. The purpose of the combing process is to extract the features and attributes of the type data blocks.

[0082] This embodiment filters the original specimen data through preset filtering rules, removes noise and invalid data, improves the quality and accuracy of the data, and reduces errors and interference in subsequent processing steps. The initial cleansed data is separated into initial image data and initial structural data through preset type rules. This type separation enables subsequent processing to be optimized and specialized for different types of data, thereby improving processing efficiency and accuracy. It is determined whether the initial image data meets the preset pixel requirements, and the second set of image data is reacquired when it does not meet the requirements. Through reacquisition and fusion processing, specimen image data that meets the requirements is finally obtained, ensuring the clarity, resolution and color accuracy of the image data, and improving the reliability of subsequent image analysis and processing. The initial structural data is divided into corresponding type data blocks using a preset multi-scale segmentation strategy, and these data blocks are processed according to preset combing rules. In this way, the characteristics and attributes of the type data blocks can be extracted, so as to better understand the structure and morphology of the specimen and provide useful information for subsequent structural analysis and comparison.

[0083] In one embodiment, node analysis processing is performed on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data, including:

[0084] First, the specimen image data is processed to extract image pixel blocks, divide the image into small blocks of pixels, calculate the similarity matrix between image pixel blocks, compare the features between different pixel blocks, such as texture, color or shape, and quantify the similarity between pixel blocks to find similar pixel blocks.

[0085] After calculating the similarity matrix, feature point recognition is performed. By analyzing the similarity matrix, pixel blocks with significant features are determined to obtain a candidate set of image feature nodes, where feature points include edges, textures or other visually prominent features in the image.

[0086] Based on the preset multi-scale spatial rules, the key nodes of the candidate set of image feature nodes are screened to obtain image node data. The multi-scale spatial rules are used to select key node data with important significance from the candidate set at different scales to obtain image node data;

[0087] Next, node analysis is performed on the specimen type data to determine the connection nodes and node types between different nodes. Through path calculation, the connection relationship in the structural data is analyzed to find the connection nodes between nodes. Based on the node type, the key nodes in the connection nodes are extracted to obtain the candidate set of feature nodes.

[0088] Finally, the node analysis of the candidate set of characteristic nodes is performed based on the preset structural connection rules, and non-critical nodes are eliminated to find nodes with key roles and connection functions in the structure. By analyzing the connection relationship between nodes and applying the connection rules, the characteristic node data is screened out.

[0089] This embodiment can better capture the details of the image by decomposing the image into pixel blocks and calculating the similarity matrix. This helps to improve the accuracy and precision of image processing tasks. By analyzing the similarity matrix and identifying feature points, pixel blocks with significant features in the image are found. These feature points play a key role in tasks such as image recognition and retrieval. By applying preset multi-scale spatial rules to image feature nodes for key node screening, key nodes can be captured at different scales. This helps to improve the comprehensive understanding and analysis capabilities of image features. Through path calculation and node type evaluation, the connection relationship between nodes in structural data is analyzed. Based on node types and preset structural connection rules, key nodes with importance and connection functions are extracted, which helps to understand the key elements and key paths in the data and provide a basis for further application and analysis.

[0090] In one embodiment, the sample image data is subjected to image segmentation processing according to the image node data to obtain a sample region image, and the sample region image is subjected to image analysis to obtain sample image information, including:

[0091] The specimen image data is processed by image segmentation using the image node data to obtain the specimen area image, and the specimen area image is analyzed to extract relevant information of the specimen image. The extraction step includes technical means such as texture analysis, shape analysis and color analysis to obtain image features that reflect the specimen status information.

[0092] Based on the image analysis, the image node data is mapped to the specimen image data to form seed nodes, which represent the areas with important features in the specimen image.

[0093] At the same time, the key feature area of ​​the specimen image data is located according to the seed node, and the key feature area includes the area of ​​interest of the specimen, such as the cell nucleus, cytoplasm or other parts with important features.

[0094] Based on the seed nodes, the regional similarity of the key feature area is calculated by comparing the texture, shape edge and pigmentation features of the key feature area.

[0095] Determine whether the regional similarity meets the preset similarity threshold. The similarity threshold is determined according to the specific application scenario and requirements and is used to determine whether the regional similarity meets the expected requirements.

[0096] If the regional similarity does not meet the similarity threshold, the corresponding seed nodes need to be remapped and the corresponding key feature regions need to be repositioned. The seed nodes need to be reselected and the positions of the key feature regions need to be re-determined to more accurately capture the important features of the specimen image.

[0097] When the region similarity meets the similarity threshold, the specimen region image is segmented into multiple levels based on the key feature region and optimized to obtain the specimen region image.

[0098] Finally, the optimized specimen area image is subjected to texture analysis, shape analysis, and color analysis to obtain specimen image information reflecting the specimen status information.

[0099] This embodiment divides the specimen image into smaller areas through the technology of image cutting and multi-level area segmentation, so that the analysis and processing of the specimen image is more refined and accurate. By mapping the image node data to the specimen image data to form a seed node, and locating the key feature area, the important feature area in the specimen image is accurately located according to the information of the image node. By calculating the regional similarity of the key feature area and comparing it with the preset similarity threshold, it is determined whether the regional similarity meets the requirements. This helps to screen out specimen area images that meet the similarity requirements and improve the accuracy and reliability of image analysis. When the regional similarity does not meet the similarity threshold, remapping the corresponding seed node and relocating the key feature area can correct the positioning deviation and select a more suitable feature area, thereby improving the processing effect of the specimen image.

[0100] In one embodiment, feature extraction is performed on the specimen type data according to the feature node data to obtain feature type data, and structural analysis is performed on the feature type data to obtain specimen type information, including:

[0101] Node pathological feature analysis is performed on the characteristic node data to obtain node characteristic data, which includes node status, number of pathological nodes, and node attributes. By analyzing the node characteristics, the relationship and characteristics between nodes can be understood.

[0102] Next, the node feature data is mapped to the specimen type data, and the node feature data is associated with the structure data of the specimen, so that the node feature information is applied to the entire specimen type data.

[0103] The mapped specimen type data is subjected to type feature analysis and extraction. By analyzing the mapped specimen type data, data describing the structural features are extracted to obtain feature type data, including information such as shape, size, and hierarchical structure, which is used to describe the structural features of the specimen.

[0104] Cluster analysis is performed on the characteristic type data to classify similar characteristic type data together to obtain type characteristic type data. Cluster analysis divides the specimen type data into different categories according to the similarity of structural characteristics.

[0105] Grid analysis is performed on feature type data to reveal the connection relationship between structures and obtain the structural connection relationship. Grid analysis reveals the overall layout and organization of the specimen structure by analyzing the connection mode and relationship between structures.

[0106] Perform state analysis on feature type data and structural connection relationships to obtain specimen state information. By analyzing the state changes of the structure, we can understand the structural characteristics and behaviors of the specimen under different conditions.

[0107] The characteristic type data, structural connection relationship and specimen status information are combined and processed to obtain complete specimen type information. By comprehensively analyzing and processing different data information, more comprehensive and accurate specimen type information can be obtained.

[0108] This embodiment obtains important feature information about the specimen structure by extracting features from the feature node data. This helps to identify and describe the structural features of the specimen, such as shape, size, and connection relationship, and provides an in-depth understanding of the specimen structure. By analyzing the feature type data, the organization mode, hierarchy, and association relationship of the specimen structure are revealed. This helps to understand the structural characteristics, functions, and evolution of the specimen, and provides a basis for further research and analysis. By performing cluster analysis on the feature type data, similar feature type data are classified into one category to achieve classification and classification description of the specimen structure. This helps to automatically classify and compare a large number of specimens, and improve work efficiency and accuracy. By performing grid analysis on the feature type data, the connection relationship and layout rules between structures can be revealed. This helps to understand the overall organization mode, spatial distribution, and interaction of the specimen structure, and provides a basis for further structural analysis and functional research.

[0109] In one embodiment, the specimen region image and feature type data are subjected to association analysis and node extraction to obtain specimen-related data and pathology-related nodes, including:

[0110] Acquire the specimen region image and feature type data, establish a mapping relationship between the specimen region image and the feature type data, map the feature type data onto the specimen region image according to the mapping relationship, and generate a corresponding specimen mapping image.

[0111] Analyze and process the specimen mapping image to identify the structural features and areas therein, analyze the brightness, color, texture and other features in the mapping image, as well as possible shape, boundary and other information, and extract feature type data in the specimen mapping image, such as key points, lines, shapes, etc.

[0112] The mapping relationship is used to match and extract the feature type data in the specimen mapping image and the overlapping nodes in the specimen area image. By comparing the feature type data in the mapping image with the features of the specimen area image, the overlapping nodes between them are determined, and the location, attributes, feature description and other information of the overlapping nodes are extracted.

[0113] According to the location and characteristics of the overlapping nodes, pathological correlation analysis is performed to determine the correlation between nodes, analyze the distance, connection mode, shape similarity and other indicators between nodes, and determine the correlation between them. According to the results of the pathological correlation analysis, the associated nodes are combined to form pathological correlation nodes.

[0114] The pathology-related nodes are mapped back to the specimen area image using the mapping relationship to determine their position and range in the original image. According to the position of the pathology-related nodes, the original image is subjected to the association connection analysis to analyze the connection mode and relationship between the nodes. The connection relationship and attribute information between the pathology-related nodes are extracted to form the association data.

[0115] This embodiment realizes the association between image and data by mapping feature type data onto the specimen area image, which enables the feature type data to be intuitively presented on the specimen area image, providing a more comprehensive and intuitive way of displaying information. Through mapping analysis and node extraction, key feature type data is extracted from the specimen mapping image. This helps to capture important features such as shape, texture, and boundary of the specimen, and provides a detailed description and quantitative analysis of the specimen structure. By performing pathological correlation analysis on overlapping nodes, the correlation relationship between nodes can be revealed. By performing correlation connection analysis on the mapping image, the connection relationship and attribute information between pathologically associated nodes can be extracted to form specimen association data. This helps to obtain information such as the overall layout, organization, and spatial distribution of the specimen structure.

[0116] In one embodiment, a comprehensive analysis is performed based on the specimen association data combined with the specimen image information and the specimen type information to obtain a specimen pathology report, and the specimen pathology report is encrypted according to the pathology association node to obtain an encrypted report, including:

[0117] Extracting corresponding connection points of specimen image information and specimen type information respectively according to specimen association data to obtain image association points and structure association points, analyzing the correlation between the image association points and the structure association points to obtain corresponding connection information, associating and connecting the specimen image information and the specimen type information according to the connection information and mapping them to a preset blank three-dimensional model to obtain a specimen three-dimensional model, performing state analysis on the specimen three-dimensional model according to the pathology association node to obtain state information, comprehensively correcting the state information according to the specimen image information and the specimen type information to obtain specimen comprehensive information, and generating a corresponding specimen pathology report based on the specimen comprehensive information;

[0118] According to the preset encryption rules, the corresponding specific node data is randomly extracted from the pathology-related nodes, the specific node data is converted into encrypted node data for encryption, the specimen node data about the node is extracted from the specimen pathology report, all the specimen node data in the specimen pathology report are replaced with the encrypted node data, and the replacement position data of the specimen node data is recorded to obtain a replacement report;

[0119] The extracted specimen node data is encrypted according to preset encryption rules to obtain corresponding encrypted data, the replacement position data is converted into a corresponding decryption password, the encrypted data, the decryption password and the replacement report are integrated to obtain an encrypted report.

[0120] This embodiment realizes a comprehensive analysis of specimen information by combining specimen association data, specimen image information and specimen type information, so that image features, structural features and associated data can be comprehensively considered when generating a specimen pathology report, providing a more comprehensive and accurate specimen analysis result. By performing association analysis on image association points and structural association points, and associating, connecting and mapping specimen image information and specimen type information, a three-dimensional model of the specimen is obtained. This helps to display the morphological structure of the specimen in a more intuitive and specific way, and provides a more in-depth observation and analysis platform. The state of the specimen three-dimensional model is analyzed based on the pathology association node to obtain state information. By comprehensively correcting the state information with the specimen image information and the specimen type information, the accuracy and completeness of the specimen state can be improved. This helps to better understand the morphological characteristics, tissue state and functional performance of the specimen. Based on the preset encryption rules, the specimen node data in the specimen pathology report is replaced with the encrypted node data, and the replacement position data is recorded. Then, the extracted specimen node data is encrypted by the encryption algorithm to obtain encrypted data. Finally, the encrypted data, decryption password and replacement report are integrated into an encrypted report. This provides encrypted protection for specimen pathology reports, ensuring the security of sensitive data.

[0121] Reference Figure 2 As shown, the present invention also provides a specimen data information processing system, which is applied to any one of the above-mentioned specimen data information processing methods, comprising:

[0122] An acquisition module, which is used to perform multi-level separation processing on the acquired original specimen data to obtain specimen image data and specimen type data;

[0123] A separation module, the separation module is used to perform node analysis and processing on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data;

[0124] The cutting module is used to perform image cutting processing on the specimen image data according to the image node data to obtain the specimen area image, perform image analysis on the specimen area image to obtain the specimen image information,

[0125] An analysis module, the analysis module is used to extract features of the specimen type data according to the feature node data to obtain feature type data, and perform structural analysis on the feature type data to obtain specimen type information;

[0126] A processing module, which is used to perform association analysis and node extraction on the specimen area image and feature type data to obtain specimen association data and pathology association nodes;

[0127] The control module is used to perform a comprehensive analysis based on the specimen association data combined with the specimen image information and the specimen type information to obtain a specimen pathology report, and encrypt the specimen pathology report according to the pathology association node to obtain an encrypted report.

[0128] The specimen data information processing system provided by the present invention is effectively divided into image data and structural data through multi-level separation processing. This process not only optimizes data management, but also lays the foundation for subsequent refined analysis. The node analysis technology is used to process image and structural data respectively, which improves the pertinence and accuracy of data processing and makes the extraction of key information more efficient. Image cutting processing is based on image node data, which can accurately segment specimen areas with specific significance, and then obtain richer image information through image analysis. At the same time, the extraction and analysis of feature type data reveals the microscopic structural characteristics inside the specimen, and the combination of the two greatly enhances the understanding and mining of deep-level information of biological specimens. Based on the comprehensive analysis of specimen-related data, image information and structural information, the generated specimen pathology report content is more comprehensive and in-depth, providing more reliable and valuable reference for scientific researchers and clinicians. The use of pathology-related nodes to encrypt the report innovatively combines bioinformatics and information security technology, which not only ensures the confidentiality of the report content, but also ensures the security in the data exchange process, which meets the current strict requirements for the protection of personal health information.

[0129] Reference Figure 3 As shown, the present invention also provides a specimen data information processing method and device, comprising:

[0130] Memory, used to store programs;

[0131] The processor is used to execute the program to implement each step of any one of the above-mentioned methods for processing sample data information.

[0132] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0133] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0134] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0135] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for processing specimen data information, characterized in that: include: Perform multi-level separation processing on the acquired original specimen data to obtain specimen image data and specimen type data; Performing node analysis processing on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data; Performing image segmentation processing on the specimen image data according to the image node data to obtain a specimen region image, performing image analysis on the specimen region image to obtain specimen image information, Extracting features of the specimen type data according to the characteristic node data to obtain characteristic type data, and performing structural analysis on the characteristic type data to obtain specimen type information; Performing association analysis and node extraction on the specimen region image and the characteristic type data to obtain specimen-related data and pathology-related nodes; Performing a comprehensive analysis based on the specimen association data combined with the specimen image information and the specimen type information to obtain a specimen pathology report, and encrypting the specimen pathology report according to the pathology association node to obtain an encrypted report; The node analysis processing is performed on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data, including: Extracting image pixel blocks of the specimen image data, obtaining an image feature node candidate set by calculating a similarity matrix of the image pixel blocks and performing feature point recognition, and performing key node screening on the image feature node candidate set at different scales based on a preset multi-scale space rule to obtain the image node data; Performing node analysis on the specimen type data to obtain connection nodes and node types, extracting key nodes from the connection nodes according to the node types to obtain a candidate set of characteristic nodes, performing node analysis on the candidate set of characteristic nodes based on a preset structural connection rule and eliminating non-key nodes to obtain the characteristic node data; The corresponding connection points of the specimen image information and the specimen type information are extracted respectively according to the specimen association data to obtain image association points and structure association points, the image association points and the structure association points are mutually correlated and analyzed to obtain corresponding connection information, the specimen image information and the specimen type information are correlated and connected according to the connection information and mapped to a preset blank three-dimensional model to obtain a specimen three-dimensional model, the specimen three-dimensional model is analyzed in state according to the pathology association node to obtain state information, the state information is comprehensively corrected according to the specimen image information and the specimen type information to obtain specimen comprehensive information, and the corresponding specimen pathology report is generated based on the specimen comprehensive information.

2. The method for processing sample data information according to claim 1, characterized in that: The obtained original specimen data is subjected to multi-level processing to obtain specimen image data and specimen type data, including: Extracting the original specimen data from the specimen tube, filtering the original specimen data according to a preset filtering rule to obtain initial cleansed data, and performing type separation on the initial cleansed data according to a preset type rule to obtain initial image data and initial structure data; Determining whether the initial image data meets the preset pixel requirement, and when the initial image data does not meet the preset pixel requirement, reacquiring second initial image data, and fusing the second initial image data with the initial image data to obtain the specimen image data; The initial structure data is segmented into corresponding type data blocks according to a preset multi-scale segmentation strategy, and the type data blocks are combed according to preset combing rules to obtain the specimen type data.

3. The method for processing specimen data information according to claim 1, characterized in that: The step of performing image segmentation processing on the specimen image data according to the image node data to obtain a specimen region image, and performing image analysis on the specimen region image to obtain specimen image information includes: Mapping the image node data to the specimen image data to form a seed node, and locating the key feature area of ​​the specimen image data, calculating the regional similarity of the key feature area based on the seed node, and judging whether the regional similarity meets a preset similarity threshold, and when the regional similarity does not meet the similarity threshold, remapping the corresponding seed node and relocating the corresponding key feature area; When the region similarity meets the similarity threshold, the specimen image data is subjected to multi-level region segmentation and optimization processing based on the key feature region to obtain the specimen region image; Texture analysis, shape analysis and color analysis are performed on the specimen region image in sequence to obtain the specimen image information reflecting the specimen state information.

4. The method for processing specimen data information according to claim 1, characterized in that: The step of extracting features from the specimen type data based on the feature node data to obtain feature type data, and performing structural analysis on the feature type data to obtain specimen type information includes: Performing node pathological feature analysis on the characteristic node data to obtain node characteristic data including node status, number of pathological nodes and node attributes, mapping the node characteristic data to the specimen type data, performing type feature analysis and extraction on the mapped specimen type data to obtain the characteristic type data; Perform cluster analysis on the feature type data to obtain feature cluster data, perform grid analysis on the feature type data to obtain structural connection relationships, perform state analysis on the feature type data and the structural connection relationships to obtain specimen state information, and combine the feature type data, the structural connection relationships and the specimen state information to obtain the specimen type information.

5. The method for processing specimen data information according to claim 1, characterized in that: The step of performing association analysis and node extraction on the specimen region image and the feature type data to obtain specimen association data and pathology association nodes includes: Mapping the characteristic type data onto the specimen region image to obtain a corresponding specimen mapping image, performing mapping analysis on the specimen mapping image to obtain a mapping relationship between the characteristic type data and the specimen region image, extracting overlapping nodes of the characteristic type data and the specimen region image from the specimen mapping image based on the mapping relationship, and performing pathological correlation analysis on the overlapping nodes to obtain the pathological correlation nodes; The mapping image is subjected to association connection analysis according to the mapping relationship and the pathology-related nodes to obtain the specimen-related data.

6. The method for processing specimen data information according to claim 1, characterized in that: The method of performing a comprehensive analysis based on the specimen association data in combination with the specimen image information and the specimen type information to obtain a specimen pathology report, and encrypting the specimen pathology report according to the pathology association node to obtain an encrypted report includes: According to a preset encryption rule, corresponding specific node data is randomly extracted from the pathology-related nodes, the specific node data is converted into encrypted node data for encryption, specimen node data about the node is extracted from the specimen pathology report, all specimen node data in the specimen pathology report are replaced with the encrypted node data, and replacement position data of the specimen node data is recorded to obtain a replacement report; The extracted specimen node data is encrypted according to preset encryption rules to obtain corresponding encrypted data, the replacement position data is converted into a corresponding decryption password, and the encrypted data, decryption password and replacement report are integrated to obtain the encrypted report.

7. A specimen data information processing system, applied to a specimen data information processing method according to any one of claims 1 to 6, characterized in that: include: An acquisition module, the acquisition module is used to perform multi-stage separation processing on the acquired original specimen data to obtain specimen image data and specimen type data; A separation module, the separation module is used to perform node analysis processing on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data; A cutting module, wherein the cutting module is used to perform image cutting processing on the specimen image data according to the image node data to obtain a specimen area image, and perform image analysis on the specimen area image to obtain specimen image information. An analysis module, the analysis module is used to extract features of the specimen type data according to the characteristic node data to obtain characteristic type data, and perform structural analysis on the characteristic type data to obtain specimen type information; A processing module, the processing module is used to perform association analysis and node extraction on the specimen area image and the feature type data to obtain specimen-related data and pathology-related nodes; A control module, the control module is used to perform a comprehensive analysis based on the specimen association data in combination with the specimen image information and the specimen type information to obtain a specimen pathology report, and encrypt the specimen pathology report according to the pathology association node to obtain an encrypted report; The node analysis processing is performed on the specimen image data and the specimen type data in sequence to obtain image node data and feature node data, including: Extracting image pixel blocks of the specimen image data, obtaining an image feature node candidate set by calculating a similarity matrix of the image pixel blocks and performing feature point recognition, and performing key node screening on the image feature node candidate set at different scales based on a preset multi-scale space rule to obtain the image node data; Node analysis is performed on the specimen type data to obtain connection nodes and node types, key nodes are extracted from the connection nodes according to the node types to obtain a candidate set of characteristic nodes, node analysis is performed on the candidate set of characteristic nodes based on preset structural connection rules and non-key nodes are eliminated to obtain the characteristic node data.

8. A method and device for processing specimen data information, characterized in that: include: Memory, used to store programs; The processor is used to execute the program to implement each step of the sample data information processing method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 6.

Images